CN112098409B - Hydrophobicity live-line testing method for composite insulator of power transmission line - Google Patents

Hydrophobicity live-line testing method for composite insulator of power transmission line Download PDF

Info

Publication number
CN112098409B
CN112098409B CN202010980059.7A CN202010980059A CN112098409B CN 112098409 B CN112098409 B CN 112098409B CN 202010980059 A CN202010980059 A CN 202010980059A CN 112098409 B CN112098409 B CN 112098409B
Authority
CN
China
Prior art keywords
composite insulator
layer
aerial vehicle
unmanned aerial
hydrophobicity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010980059.7A
Other languages
Chinese (zh)
Other versions
CN112098409A (en
Inventor
李玉伟
杜立江
邵震
王胜丹
吴述伟
段红涛
盛从兵
黄桥林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Puyang Power Supply Co of State Grid Henan Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Puyang Power Supply Co of State Grid Henan Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Puyang Power Supply Co of State Grid Henan Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202010980059.7A priority Critical patent/CN112098409B/en
Publication of CN112098409A publication Critical patent/CN112098409A/en
Application granted granted Critical
Publication of CN112098409B publication Critical patent/CN112098409B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
    • G01R19/145—Indicating the presence of current or voltage
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Analytical Chemistry (AREA)
  • Immunology (AREA)
  • Biochemistry (AREA)
  • Pathology (AREA)
  • Chemical & Material Sciences (AREA)
  • Insulators (AREA)

Abstract

The invention discloses a method for testing hydrophobicity of a composite insulator of a power transmission line in an electrified way, which comprises the following steps: collecting a composite insulator water covering image and a corresponding hydrophobicity grade to establish a sample data set; building a convolutional neural network model based on VGGNet, and training the convolutional neural network model by using a sample data set to obtain a composite insulator hydrophobicity grade judgment model; calculating the flight safety distance of the unmanned aerial vehicle according to the disturbance state of the unmanned aerial vehicle on the electromagnetic field around the power transmission line; and the unmanned aerial vehicle flies in the power transmission line according to the flight safety distance to acquire a new composite insulator water covering image, and performs hydrophobicity grade judgment on the new composite insulator water covering image by adopting a grid analysis method based on the composite insulator hydrophobicity grade judgment model to obtain a composite insulator hydrophobicity grade distribution diagram. The method can directly judge the hydrophobicity grade of the composite insulator.

Description

Hydrophobicity live-line testing method for composite insulator of power transmission line
Technical Field
The invention belongs to the technical field of power grid equipment state detection, and particularly relates to a hydrophobicity live-line test method for a composite insulator of a power transmission line.
Background
The hydrophobicity detection is an important means for judging the anti-pollution flashover performance of the composite insulator, and the regular hydrophobicity detection of the suspended composite insulator is an important guarantee for ensuring the safe operation of a power grid. In engineering application, a water spraying grading method is mostly adopted for hydrophobicity detection, namely, the surface of the umbrella skirt of the composite insulator is sprayed with water in a mist shape, and hydrophobicity grade judgment is carried out according to the distribution form of water drops on the surface of the umbrella skirt. However, the traditional water spraying classification method needs workers to climb a tower or carry an aerial ladder to approach a net hanging insulator to complete water spraying operation, and the judgment of the hydrophobicity grade of the insulator is often empirically evaluated in a visual inspection mode. Obviously, the method has strong experience dependence, poor safety and low efficiency, the standardization and the digitization degrees are all required to be improved, and in addition, in order to ensure the safety of workers in the detection, the line to be detected generally needs to be temporarily powered off, so that the reliability of a power grid is reduced, and certain economic loss is caused.
In recent years, with the development of electronic technology and computer technology, hand-held water spraying equipment gradually completes the conversion from mechanical pressing type to electronic driving type, and reasonable insulation design can realize the live test of the hydrophobic state of the composite insulator, which improves the automation level of hydrophobic detection to a certain extent, but the detection process still does not leave manual ascending and experience judgment, so the defects of low detection efficiency and poor safety are not compensated. Fixed automatic water spraying devices are adopted in part of regions, separation of workers and detection areas is achieved by combining camera monitoring and remote control, but detection equipment installation is required to be carried out on each test point in the mode, and actual requirements can obviously not be met.
Disclosure of Invention
Aiming at the problems of low efficiency and poor accuracy of the traditional composite insulator hydrophobicity detection method, the invention provides the live-line detection method for the hydrophobicity of the composite insulator of the power transmission line, which replaces the hydrophobicity detection operation mode of manual ascending, gets rid of experience dependence, improves the detection safety and the detection efficiency, and can analyze and process the target insulator water covering image in real time and quickly distinguish the hydrophobicity grade of the composite insulator by the constructed composite insulator hydrophobicity grade judgment model.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a method for testing hydrophobicity of a composite insulator of a power transmission line in an electrified manner comprises the following steps:
s1, collecting a composite insulator water covering image and a corresponding hydrophobicity grade to establish a sample data set;
s2, constructing a convolutional neural network model based on VGGNet, and training the convolutional neural network model by using the sample data set obtained in the step S1 to obtain a composite insulator hydrophobicity grade judgment model;
s3, calculating the flight safety distance of the unmanned aerial vehicle according to the disturbance state of the unmanned aerial vehicle on the electromagnetic field around the power transmission line;
and S4, the unmanned aerial vehicle flies in the power transmission line according to the flying safety distance calculated in the step S3 to acquire a new composite insulator water covering image, and performs hydrophobicity grade judgment on the new composite insulator water covering image by adopting a grid analysis method based on the composite insulator hydrophobicity grade judgment model to acquire a composite insulator hydrophobicity grade distribution diagram.
In step S3, a formula corresponding to the disturbance state of the electromagnetic field around the power transmission line by the unmanned aerial vehicle is as follows:
E＝5.9168R -0.621 ；
in the formula, E represents the electromagnetic field intensity around the power transmission line where the unmanned aerial vehicle is located, and R represents the distance from the projection point of the geometric center of the unmanned aerial vehicle on the straight line where the inner edge of the wing is located to the center of the field source.
The step S2 includes the steps of:
s2.1, constructing a convolutional neural network model containing an input layer, a hidden layer and an output layer based on VGGNet;
s2.2, setting a precision threshold delta;
s2.3, inputting the sample data set into a convolutional neural network model by using a cross-folding verification method to obtain a composite insulator hydrophobicity grade judgment model, and calculating an accuracy value v of the composite insulator hydrophobicity grade judgment model;
s2.4, comparing the precision value v with a precision threshold value delta, if v is less than delta, executing a step S2.5, and if v is more than or equal to delta, executing a step S3;
and S2.5, rotating the composite insulator water-covered image in the sample data set to form an amplification data set, updating the sample data set according to the amplification data set, and returning to the step S2.3.
In step S2.1, the hidden layer includes 13 convolutional layers, 3 fully-connected layers, and 5 pooling layers, and the connection relationship among the input layer, convolutional layers, fully-connected layers, pooling layers, and output layer in the convolutional neural network model is: convolution layer I-convolution layer II-pooling layer I-convolution layer III-convolution layer IV-pooling layer II-convolution layer V-convolution layer VI-convolution layer VII-pooling layer III-convolution layer VIII-convolution layer IX-convolution layer X-pooling layer IV-convolution layer XI-convolution layer XII-pooling layer V-full connection layer I-full connection layer II-full connection layer III-output layer.
The sizes of the 13 convolutional layer convolution kernels are all 3*3, the step lengths are all 1, the same filling is adopted, and the corresponding activation functions are all RELU; the 5 pooling layers all adopt a maximum pooling mode, have the step length of 2 and are not filled; the output layer is realized by adopting a softmax classifier.
The step S4 includes the steps of:
s4.1, acquiring a new composite insulator water covering image by using an unmanned aerial vehicle;
s4.2, respectively dividing the new composite insulator water-covered image into a plurality of non-overlapping sub-images, and recording the position of each sub-image in the composite insulator water-covered image, wherein the pixel of each sub-image is 256 × 256;
and S4.3, respectively judging the hydrophobicity grade of each sub-image by using the composite insulator hydrophobicity grade judging model, and integrating the judging result corresponding to each sub-image according to the position of the sub-image to obtain the required composite insulator hydrophobicity grade distribution map.
The invention has the beneficial effects that: the method has the advantages that the unmanned aerial vehicle acquires the water covering image of the composite insulator, and the hydrophobicity grade of the composite insulator is directly judged and output by using the hydrophobicity grade judging model of the composite insulator, so that the traditional hydrophobicity detecting mode is changed, the dependence on human experience is eliminated, and the hydrophobicity detection of the power transmission line is more standardized, convenient, visualized and intelligent; the working mode is simple, personnel are not needed to climb the tower, the labor intensity is reduced, the safety of the personnel is ensured, and the detection efficiency is greatly improved; the unmanned aerial vehicle flies in a safe distance and acquires images, so that the interference of the unmanned aerial vehicle on the power transmission line is avoided, and the safe operation of the unmanned aerial vehicle and the power transmission line is ensured; the high-efficiency flexibility of the unmanned aerial vehicle provides possibility for shortening the polling period and increasing polling points, is favorable for timely finding and solving the hidden danger of the power grid operation, improves the power grid operation reliability, and has important significance for establishing a modern power grid polling mode.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a convolutional neural network model.
Fig. 2 is a schematic diagram of the distance d of the inner edge of the wing of the drone from the geometric center of the split conductor and the horizontal height h of the geometric center of the drone from the plane of the split conductor.
FIG. 3 is a schematic flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
A method for testing hydrophobicity of a composite insulator of a power transmission line in an electrified way is shown in figure 3 and comprises the following steps:
s1, collecting a composite insulator water covering image and a corresponding hydrophobicity grade to establish a sample data set;
the composite insulator water covering image can be obtained by an image acquisition device such as a man-machine or an unmanned aerial vehicle, and the composite insulator water covering image is measured by a professional laboratory according to the international hydrophobicity grade; or, the sample data set may also directly adopt the international hydrophobicity standard image and the corresponding hydrophobicity grade classification data. The sample data set comprises input data and output data, namely the composite insulator water covering image and the corresponding hydrophobicity grade.
S2, constructing a convolutional neural network model based on VGGNet, training the convolutional neural network model by using the sample data set obtained in the step S1 to obtain a composite insulator hydrophobicity grade judgment model, and the method comprises the following steps:
s2.1, building a convolutional neural network model comprising an input layer, a hidden layer and an output layer based on VGGNet, as shown in FIG. 1.
The hidden layer comprises 13 convolutional layers, 3 full-connection layers and 5 pooling layers, and the connection relation among the input layer, the convolutional layers, the full-connection layers, the pooling layers and the output layer in the convolutional neural network model is as follows: the multilayer comprises a convolutional layer I, a convolutional layer II, a pooling layer I, a convolutional layer III, a convolutional layer IV, a pooling layer II, a convolutional layer V, a convolutional layer VI, a convolutional layer VII, a pooling layer III, a convolutional layer VIII, a convolutional layer IX, a convolutional layer X, a pooling layer IV, a convolutional layer XI, a convolutional layer XII, a pooling layer V, a full connecting layer I, a full connecting layer II, a full connecting layer III and an output layer.
The number of the neurons of the full connecting layer I, the full connecting layer II and the full connecting layer III is 4096, 4096 and 1000; the sizes of 13 convolutional layer convolutional kernels in the convolutional neural network model are all 3*3, the step lengths are all 1, the same filling is adopted, and the corresponding activation functions are all RELUs; the 5 pooling layers all adopt a maximum pooling mode, the step length is 2, and no filling is performed; the output layer is realized by adopting a softmax classifier. The convolutional neural network model can keep the size of the output characteristic diagram in each convolutional layer unchanged, the number of channels is doubled, the size of the output characteristic diagram in each pooling layer is halved, the topological structure of the neural network is simplified, and a good effect is achieved.
And S2.2, setting a precision threshold value delta.
The precision threshold δ is not less than 90%.
And S2.3, inputting the sample data into the convolutional neural network model by using a ten-fold cross validation method to obtain a composite insulator hydrophobicity grade judgment model, and calculating the precision value v of the composite insulator hydrophobicity grade judgment model.
Dividing the sample data set obtained in the step S1 into ten parts by using a ten-fold cross-validation method, and taking 9 parts of the sample data set as training samples and 1 part of the sample data set as test samples in turn; firstly, training a convolutional neural network model by using 9 training samples of a first round to obtain a corresponding composite insulator hydrophobicity grade judgment model, inputting 1 test sample of the first round into the composite insulator hydrophobicity grade judgment model to predict hydrophobicity grade, and comparing the predicted hydrophobicity grade with data in the test sample of the first round to calculate the precision value v of the first round 1 (ii) a Then, respectively training the hydrophobicity grade judgment model of the composite insulator in the previous round according to the method, calculating precision values of other rounds, and finally calculating a mean value of the precision values.
The calculation formula of the precision value v is as follows:
Figure BDA0002687208880000041
in the formula, v j And expressing the precision value corresponding to the j-th composite insulator hydrophobicity grade judgment model.
S2.4, comparing the precision value v with a precision threshold value delta, if v is less than or equal to delta, executing the step S2.5, and if v is more than delta, executing the step S3.
And S2.5, rotating the composite insulator water-covered image in the sample data set to form an amplification data set, updating the sample data set, and returning to the step S2.3.
The study sample of the composite insulator water covering image can be increased by rotating the composite insulator water covering image, so that the judgment precision of the composite insulator hydrophobicity grade judgment model can be better corrected.
S3, calculating the flight safety distance of the unmanned aerial vehicle according to the disturbance state of the unmanned aerial vehicle on the electromagnetic field around the power transmission line;
because unmanned aerial vehicle receives the effect of high voltage strong electric field when getting into around the electric power transmission line, inductive charge can appear in the metal parts on the unmanned aerial vehicle, and especially unmanned aerial vehicle surface and tip department can induce higher electric field intensity distribution to arouse electric power transmission line electric field distribution's around change. When local field intensity surpassed air puncture field intensity, the point discharge phenomenon will take place, threatens the safe operation of unmanned aerial vehicle and power transmission line. For the overhead transmission line of 10kV-750kV, the working frequency is 50Hz, and the problem of electric field distribution can be approximately considered as the problem of electrostatic field to study. At this time, the field source is the potential distribution of the transmission line, and the field quantity to be analyzed is the spatial electric field strength or potential distribution.
The electrostatic field is an active non-rotating field and meets the following basic rules:
▽·D＝ρ；
in the formula, rho represents the charge density on the unmanned aerial vehicle, D represents a potential displacement vector, and D represents the dispersion of the potential displacement vector;
▽×E＝0；
in the formula, E represents the electric field strength around the power transmission line;
the medium composition equation is as follows:
D＝εE；
wherein epsilon represents the dielectric constant of the unmanned aerial vehicle housing;
in the field space around the transmission line, the potential
Figure BDA0002687208880000051
Satisfies the Laplace criterionThe equation:
Figure BDA0002687208880000052
according to the dirichlet boundary conditions:
Figure BDA0002687208880000053
in the formula (I), the compound is shown in the specification,
Figure BDA0002687208880000054
representing the potential, V, on the transmission line line Representing the voltage on the transmission line;
Figure BDA0002687208880000055
in the formula (I), the compound is shown in the specification,
Figure BDA0002687208880000056
represents a potential at infinity>
Figure BDA0002687208880000057
Represents the potential of the earth, is greater than or equal to>
Figure BDA0002687208880000058
And indicating the potential on the high-voltage tower where the transmission line is positioned.
Establishing simulation models of the composite insulator, the high-voltage tower and the unmanned aerial vehicle in sequence through finite element analysis software, further obtaining a simulation model of the unmanned aerial vehicle entering the high-voltage transmission line, and according to the formula, the electric field intensity E and the electric potential
Figure BDA0002687208880000059
The boundary value problem is solved by the relation, and the field intensity distribution characteristics of the unmanned aerial vehicle from different positions of the power transmission line can be obtained.
The electric field intensity E and potential
Figure BDA00026872088800000510
The relationship of (1) is:
Figure BDA0002687208880000061
as shown in fig. 2, a relationship between a distance R from a projection point of a straight line of the geometric center of the unmanned aerial vehicle on the wing inner edge to the center of the field source, a distance d from the wing inner edge to the geometric center of the split conductor of the unmanned aerial vehicle, and a horizontal height h from the geometric center of the unmanned aerial vehicle to the plane of the split conductor is established at the same time:
Figure BDA0002687208880000062
the distance R is the distance between the unmanned aerial vehicle and the power transmission line, and when the distance between the unmanned aerial vehicle and the power transmission line is R, the field intensity distribution characteristic E (R) of the position point which is R away from the power transmission line is as follows:
Figure BDA0002687208880000063
in the formula, ρ r And V represents the solving space.
Under the unchangeable condition in field source condition, learn according to singing the chamber distribution characteristic, electric field strength E and distance r's square become the inverse function relation, and the geometry of considering unmanned aerial vehicle can lead to electric field strongest point position constantly to change, so adopt power series to fit data, can obtain:
E＝5.9168R -0.621 ；
the minimum value of the safety distance can be obtained by substituting the air breakdown field strength into the formula.
S4, the unmanned aerial vehicle flies in the power transmission line according to the flying safety distance calculated in the step S3, a new composite insulator water covering image is collected, the hydrophobicity grade of the new composite insulator water covering image is judged by adopting a grid analysis method based on the composite insulator hydrophobicity grade judgment model, and a composite insulator hydrophobicity grade distribution diagram is obtained, and the method comprises the following steps:
s4.1, acquiring a new composite insulator water covering image by using an unmanned aerial vehicle;
unmanned aerial vehicle flies according to flight safety distance, utilizes the automatic water jet equipment on the unmanned aerial vehicle to spray water to composite insulator, then adopts the last image acquisition device of unmanned aerial vehicle to shoot composite insulator after the water spray, obtains new composite insulator and covers the water image.
S4.2, respectively dividing the new composite insulator water-covered image into a plurality of non-overlapping sub-images, and recording the position of each sub-image in the composite insulator water-covered image, wherein the pixel of each sub-image is 256 × 256;
and S4.3, respectively judging the hydrophobicity grade of each sub-image by using the composite insulator hydrophobicity grade judging model, and integrating the judging result corresponding to each sub-image according to the position of the sub-image to obtain the required composite insulator hydrophobicity grade distribution map.
The invention breaks away from the traditional photo by the way of dividing and integrating, one insulator can only obtain a dead plate way of one hydrophobicity grade, the hydrophobicity conditions of all positions of each composite insulator can not be completely consistent, the composite insulator used for 1 year is relatively light in aging condition, and most of the hydrophobicity grades of the insulator sheets are between HC1 and HC 3; the aging condition of the composite insulator used for 3 years is serious, and most of the existing composite insulators have hydrophobic property grades of more than HC 4. Due to the introduction of the method, the hydrophobicity analysis of the insulator is more refined and practical, and more accurate distribution conditions of the parts with serious aging of the composite insulator are provided for workers.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.

Claims (4)

1. A hydrophobicity live-line test method for a composite insulator of a power transmission line is characterized by comprising the following steps:
s1, collecting a composite insulator water covering image and a corresponding hydrophobicity grade to establish a sample data set;
s2, constructing a convolutional neural network model based on VGGNet, and training the convolutional neural network model by using the sample data set obtained in the step S1 to obtain a composite insulator hydrophobicity grade judgment model;
the step S2 includes the steps of:
s2.1, constructing a convolutional neural network model containing an input layer, a hidden layer and an output layer based on VGGNet;
s2.2, setting a precision threshold valueδ；
S2.3, inputting the sample data set into a convolutional neural network model by using a cross-folding verification method to obtain a composite insulator hydrophobicity grade judgment model, and calculating the precision value of the composite insulator hydrophobicity grade judgment modelv；
S2.4, comparing the precision valuevAnd precision thresholdδMake a comparison ifv＜δGo to step S2.5, ifv≥δIf yes, executing step S3;
s2.5, rotating the composite insulator water-covered image in the sample data set to form an amplification data set, updating the sample data set according to the amplification data set, and returning to the step S2.3;
s3, calculating the flight safety distance of the unmanned aerial vehicle according to the disturbance state of the unmanned aerial vehicle on the electromagnetic field around the power transmission line;
establishing simulation models of the composite insulator, the high-voltage tower and the unmanned aerial vehicle in sequence through finite element analysis software, further obtaining a simulation model of the unmanned aerial vehicle entering the high-voltage transmission line, solving a boundary value problem according to the relation between the electric field intensity E and the electric potential, and solving field intensity distribution characteristics of the unmanned aerial vehicle at different positions away from the transmission line; establishing a relation between a distance R from a projection point of a straight line of the geometric center of the unmanned aerial vehicle on the inner edge of the wing to the center of the field source, a distance d from the inner edge of the wing of the unmanned aerial vehicle to the geometric center of the split conductor and a horizontal height h from the geometric center of the unmanned aerial vehicle to the plane of the split conductor; when the distance between the unmanned aerial vehicle and the power transmission line is R, obtaining the field intensity distribution characteristic E (R) of a position point R away from the power transmission line; under the condition of unchanged source conditions, according to the field intensity distribution characteristics, the square of the electric field intensity E and the distance r forms an inverse function relationship, considering that the geometric shape of the unmanned aerial vehicle can cause the position of the strongest point of the electric field to be continuously changed, therefore, the power series is adopted to fit the data, and the formula of the unmanned aerial vehicle corresponding to the electromagnetic field disturbance state around the power transmission line is obtained as follows:
E＝5.9168R -0.621 ；
in the formula, E represents the electromagnetic field intensity around the power transmission line where the unmanned aerial vehicle is located;
and S4, the unmanned aerial vehicle flies in the power transmission line according to the flying safety distance calculated in the step S3 to acquire a new composite insulator water covering image, and performs hydrophobicity grade judgment on the new composite insulator water covering image by adopting a grid analysis method based on the composite insulator hydrophobicity grade judgment model to acquire a composite insulator hydrophobicity grade distribution diagram.
2. The hydrophobicity live-line test method for the composite insulator of the power transmission line according to claim 1, wherein in step S2.1, the hidden layer comprises 13 convolutional layers, 3 full-connection layers and 5 pooling layers, and connection relations among the input layer, the convolutional layers, the full-connection layers, the pooling layers and the output layer in the convolutional neural network model are as follows: the multilayer comprises a convolutional layer I, a convolutional layer II, a pooling layer I, a convolutional layer III, a convolutional layer IV, a pooling layer II, a convolutional layer V, a convolutional layer VI, a convolutional layer VII, a pooling layer III, a convolutional layer VIII, a convolutional layer IX, a convolutional layer X, a pooling layer IV, a convolutional layer XI, a convolutional layer XII, a pooling layer V, a full connecting layer I, a full connecting layer II, a full connecting layer III and an output layer.
3. The hydrophobicity live-line test method for the composite insulator of the power transmission line according to claim 2, wherein the sizes of the 13 convolution kernels are all 3*3, the step lengths are all 1, the same filling is adopted, and the corresponding activation functions are all RELUs; the 5 pooling layers all adopt a maximum pooling mode, have the step length of 2 and are not filled; the output layer is realized by adopting a softmax classifier.
4. The hydrophobicity live-line test method for the composite insulator of the power transmission line according to claim 1 or 3, wherein the step S4 comprises the following steps:
s4.1, acquiring a new composite insulator water covering image by using an unmanned aerial vehicle;
s4.2, respectively dividing the new composite insulator water-covered image into a plurality of non-overlapping sub-images, and recording the position of each sub-image in the composite insulator water-covered image, wherein the pixel of each sub-image is 256 × 256;
and S4.3, respectively judging the hydrophobicity grade of each sub-image by using the composite insulator hydrophobicity grade judging model, and integrating the judging result corresponding to each sub-image according to the position of the sub-image to obtain the required composite insulator hydrophobicity grade distribution map.
CN202010980059.7A 2020-09-17 2020-09-17 Hydrophobicity live-line testing method for composite insulator of power transmission line Active CN112098409B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010980059.7A CN112098409B (en) 2020-09-17 2020-09-17 Hydrophobicity live-line testing method for composite insulator of power transmission line

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010980059.7A CN112098409B (en) 2020-09-17 2020-09-17 Hydrophobicity live-line testing method for composite insulator of power transmission line

Publications (2)

Publication Number Publication Date
CN112098409A CN112098409A (en) 2020-12-18
CN112098409B true CN112098409B (en) 2023-04-07

Family

ID=73760263

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010980059.7A Active CN112098409B (en) 2020-09-17 2020-09-17 Hydrophobicity live-line testing method for composite insulator of power transmission line

Country Status (1)

Country Link
CN (1) CN112098409B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113255690B (en) * 2021-04-15 2022-04-12 南昌大学 Composite insulator hydrophobicity detection method based on lightweight convolutional neural network
CN113537385B (en) * 2021-08-01 2023-12-05 国网冀北电力有限公司超高压分公司 Electric composite insulator hydrophobicity classification method based on TX2 equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2002366790A1 (en) * 2001-12-12 2003-07-09 The Procter And Gamble Company Method for cleaning a soiled article
CN108205088A (en) * 2017-12-25 2018-06-26 重庆大学 A kind of parallel radio interference of high voltage ac/dc circuit calculates and optimization method
CN111667473A (en) * 2020-06-08 2020-09-15 国网新疆电力有限公司乌鲁木齐供电公司 Insulator hydrophobicity grade judging method based on improved Canny algorithm

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102591355B (en) * 2012-02-24 2014-06-11 山东电力研究院 Method for detecting safe power-line-cruising distance of UAV (unmanned aerial vehicle)
CN103440495B (en) * 2013-07-31 2016-10-05 华北电力大学（保定） A kind of composite insulator hydrophobic grade automatic identifying method
CN107219854A (en) * 2017-07-19 2017-09-29 国家电网公司 A kind of insulator hydrophobicity detection means and method based on unmanned plane
CN108009629A (en) * 2017-11-20 2018-05-08 天津大学 A kind of station symbol dividing method based on full convolution station symbol segmentation network
CN108563906B (en) * 2018-05-02 2022-03-22 北京航空航天大学 Short fiber reinforced composite material macroscopic performance prediction method based on deep learning
CN108872020A (en) * 2018-05-29 2018-11-23 国网甘肃省电力公司电力科学研究院 A kind of Hydrophobicity of Composite Insulator detection device and detection method based on unmanned air vehicle technique
CN108760740B (en) * 2018-05-31 2020-10-02 同济大学 Quick detection method for road surface skid resistance based on machine vision
CN109145985A (en) * 2018-08-21 2019-01-04 佛山职业技术学院 A kind of detection and classification method of Fabric Defects Inspection
CN111368702B (en) * 2020-02-28 2023-03-14 西安工程大学 Composite insulator hydrophobicity grade identification method based on YOLOv3 network
CN111429497B (en) * 2020-03-20 2023-05-05 郑州轻工业大学 Self-adaptive CU splitting decision method based on deep learning and multi-feature fusion

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2002366790A1 (en) * 2001-12-12 2003-07-09 The Procter And Gamble Company Method for cleaning a soiled article
CN108205088A (en) * 2017-12-25 2018-06-26 重庆大学 A kind of parallel radio interference of high voltage ac/dc circuit calculates and optimization method
CN111667473A (en) * 2020-06-08 2020-09-15 国网新疆电力有限公司乌鲁木齐供电公司 Insulator hydrophobicity grade judging method based on improved Canny algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
某型超低空无人机设计特点与关键技术分析;徐正荣;《南京航空航天大学学报》(第03期);全文 *

Also Published As

Publication number Publication date
CN112098409A (en) 2020-12-18

Similar Documents

Publication Publication Date Title
CN112098409B (en) Hydrophobicity live-line testing method for composite insulator of power transmission line
US20210073692A1 (en) Method and system for utility infrastructure condition monitoring, detection and response
CN109799442B (en) Insulator pollution flashover prediction method and system based on airborne hyperspectrum
WO2016184308A1 (en) Method for obstacle avoidance during unmanned aerial vehicle routing inspection of high-voltage double-circuit power transmission lines on same tower based on change rate of electric field intensity
CN108614274B (en) Cross type crossing line distance measuring method and device based on multi-rotor unmanned aerial vehicle
CN109300118B (en) High-voltage power line unmanned aerial vehicle inspection method based on RGB image
CN110009037B (en) Short-term engineering wind speed prediction method and system based on physical information coupling
CN106326808A (en) Method for detecting bird nests in power transmission line poles based on unmanned plane images
CN106570853A (en) Shape and color integration insulator identification and defect detection method
CN111506093A (en) Unmanned aerial vehicle-based power inspection system and method
CN111986238B (en) Concrete arch dam modal shape identification method based on unmanned aerial vehicle video shooting
CN111855500A (en) Intelligent composite insulator aging degree detection method based on deep learning
CN112684806A (en) Electric power inspection unmanned aerial vehicle system based on dual obstacle avoidance and intelligent identification
CN111157530A (en) Unmanned aerial vehicle-based safety detection method for power transmission line
CN113051423A (en) Intelligent online monitoring method for state of power transmission line of intelligent power grid based on big data analysis
AU2023278096A1 (en) Method and system for utility power lines vegetation proximity monitoring and controlling
CN116258980A (en) Unmanned aerial vehicle distributed photovoltaic power station inspection method based on vision
CN112150412A (en) Insulator self-explosion defect detection method based on projection curve analysis
CN113674512B (en) On-line monitoring and early warning system and method for electrified crossing construction site
CN116363537B (en) Method and system for identifying hidden danger of hanging objects outside transformer substation
CN113569644A (en) Airport bird target detection method based on machine vision
CN103198326B (en) A kind of image classification method of transmission line of electricity helicopter routing inspection
CN112270234A (en) Power transmission line insulation sub-target identification method based on aerial image
CN108470141A (en) Insulator recognition methods in a kind of distribution line based on statistical nature and machine learning
CN114370898A (en) Icing galloping integrated monitoring system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant